Spatio-Temporal Querying in Video Databases

Abstract

In this paper a video data model that allows efficient and effective representation and querying of spatio-temporal properties of objects is presented. The data model is focused on the semantic content of video streams. Objects, events, activities performed by objects are main interests of the model. The model supports fuzzy spatial queries including querying spatial relationships between objects and querying the trajectories of objects. The model is flexible enough to define new spatial relationship types between objects without changing the basic data model. A prototype of the proposed model has been implemented. The prototype allows various spatio-temporal queries along with the fuzzy ones and it is prone to implement compound queries without major changes in the data model.

Structural and Event Based Multimodal Video Data Modeling

“…We follow divide and conquer approach in query processing to answer complex, very long, nested and conjunctive spatial, temporal, content-based and possibly fuzzy video queries. This approach gives us the ability to deal with much more complex queries different than ones in [2] and [3]. 4.…”

“…Because there is always some unknown spatial information, the video data querying system should consider possible fuzzy queries. Fuzzy queries are constructed by giving some threshold value and they may involve some fuzzy conditions as explained in [3]. For example:…”

“…and John is implicitly found as given in Table 4.3. Then the positions of both video objects in a particular time are compared according to given fuzzy value [3] to find the solution)…”

“…al. define membership functions in [3] by using membership value (µ). The membership value of the relationship is calculated using the angle between the line connecting the centres of rectangles and the x-axis.…”

Rekall: Specifying Video Events using Compositions of Spatiotemporal Labels

“…To explore the utility of a query-based approach for detecting novel events of interest in video, we introduce REKALL, a library that exposes a data model and programming model for compositional video event specification. REKALL adapts ideas from multimedia databases [4,15,23,31,32,36,40] to the modern video analysis landscape, where using the outputs of modern machine learning techniques allows for more powerful and expressive queries, and adapts ideas from complex event processing systems for temporal data streams [8,16,25] to the spatiotemporal domain of video.…”